Image processor for character recognition

Abstract

In image processing of a document having image data of a document including an image with character images on a background image, the character images and the background image thereof are separated. First, areas in correspondence to the character images from the image data are extracted, and character code data are generated based on the extracted areas in the image data. On the other hand, the character image in the image data is replaced with the background image. The character images are reproduced with reference to the character code data at the positions of the character images. On the other hand, the original character images are deleted from the image data. The character images on the background image is complemented based on the background image data. Then the character images based on the character code data and the background image thereof are synthesized.

1. A method of image processing comprising the steps of:
 receiving image data of an original image, the original image having character images provided on a background image; 
 conducting character recognition on the image data including
 preprocessing the image data for character recognition; 
 extracting areas from the image data which correspond to the character images; and 
 generating character code data based on the extracted character images; 
 
 changing, based on the character recognition, the image data by replacing the extracted areas with the background image with reference to the image data therein generating changed image data representing an image which is same as the original image except without the character images; and 
 storing the changed image data and the character code data along with a relationship between them. 
 
   
   
     2. The method according to  claim 1 , wherein, in the generating step, the character code data are generated in reference to color information on the character images. 
   
   
     3. A method of image processing comprising the steps of:
 conducting character recognition on image data including
 preprocessing the image data for character recognition; and 
 converting character images in the preprocessed image data of an original image to character code data; and 
 complementing, based upon the character recognition, the character images based on image data around the character images therein changing image data representing an image which is same as the original image except without the character images. 
 
 
   
   
     4. The method according to  claim 3 , wherein, in the converting step, the character code data are generated in reference to color information on the character images. 
   
   
     5. A method of image processing comprising the steps of:
 conducting character recognition on image data including
 preprocessing the image data for character recognition; and 
 converting character images in the preprocessed image data of an original image to character code data; 
 
 complementing, based upon the character recognition, the character images based on image data around the character images therein generating changed image data representing an image which is same as the original image except without the character images; and 
 storing the character code data and the changed image data along with a relationship between them. 
 
   
   
     6. The method according to  claim 5 , wherein, in the converting step, the character code data are generated in reference to color information on the character images. 
   
   
     7. An image processor comprising:
 a reader which reads an original image of a document to provide image data thereof; 
 character recognition device conducting character recognition on the image data including
 a preprocessing device preprocessing the image data for character recognition; 
 a converter which determines character code data of character images in correspondence to character image in the image data; and 
 an acquiring device which determines position data on a position in the character images converted to character code data in the image data; 
 
 a corrector which, based upon the character recognition, changes the character images to the same as a color of an image around the character image with reference to the image data therein generating changed image data representing an image which is same as the original image except without the character images; and 
 a storage device which stores the character code data and the changed image data including the complemented character images along with a relationship between them. 
 
   
   
     8. The image processor according to  claim 7 , wherein said acquiring device further determines font and font size based on the character images in correspondence to the character image in the image data. 
   
   
     9. The image processor according to  claim 7 , further comprising a processor which generates print data for printing the document image, based on the character code data, the position data and the image data stored in said storage device. 
   
   
     10. The image processor according to  claim 7 , wherein the converter determines the character code data in reference to color information on the character images. 
   
   
     11. An image processor which converts character images in image data to character code data comprising:
 character recognition device conducting character recognition on the image data including
 a preprocessing device preprocessing the image data for character recognition; 
 an extractor which extracts character images in the preprocessed image data of an original image, the original image having character images provided on a background image; and 
 a converter which converts the extracted character images to character code data; 
 
 a deleter which, based on the character recognition, deletes the character images from the background image with reference to the image data therein generating changed image data representing an image which is same as the original image except without the character images; and 
 a synthesizer which synthesizes the character code data with the changed image data. 
 
   
   
     12. The image processor according to  claim 11 , wherein said deleter complements the image data at an area of the character images on the background image according to image data of an ambient background image of the area. 
   
   
     13. The image processor according to  claim 11 , wherein said converter does not convert a character image to a character code data when an area of the character image has color change. 
   
   
     14. The image processor according to  claim 11 , wherein said extractor extracts character images character by character. 
   
   
     15. The image processor according to  claim 11 , wherein said extractor extracts the character images in the unit of word. 
   
   
     16. The image processor according to  claim 11 , wherein the converter converts the extracted character images to the character code data in reference to color information on the character images. 
   
   
     17. A method of image processing comprising the steps of:
 receiving image data of an original image, the original image having at least one character image on a background image; 
 conducting character recognition on the image data including
 preprocessing the image data for character recognition; and 
 generating character code data based on the at least one character image with reference to color information on the at least one character image; 
 
 generating, based on the character recognition, changed image data representing an image which is same as the original image except without the at least one character image by replacing image data of the at least one character image that has been converted into the character code data with image data of the background image; and 
 storing the changed image data and the character code data along with a relationship between them.